© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10291
    Prev
    Next
    INDEX
    Explanations

    The neuron predominantly activates on words that serve as the first element in hyphenated compounds (i.e. the tokens immediately before a “-”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (“
    0.86
     (
    0.86
     ("
    0.81
     («
    0.68
     (?)
    0.68
     distinguishes
    0.65
     logarithms
    0.65
     (−
    0.64
     poultry
    0.63
     acrylate
    0.63
    POSITIVE LOGITS
    们的
    0.93
    들에
    0.88
    들과
    0.88
    들이
    0.87
    들을
    0.83
    들의
    0.75
    들에게
    0.75
    हरु
    0.73
     pequeñas
    0.73
     stesse
    0.73
    Activations Density 0.000%

    No Known Activations